Sequential Recommender System based on Hierarchical Attention Networks

Ying, Haochao; Zhuang, Fuzhen; Zhang, Fuzheng; Liu, Yanchi; Xu, Guandong; Xie, Xing; Xiong, Hui; Wu, Jian

doi:10.24963/ijcai.2018/546

Cited by 286 publications

(165 citation statements)

References 19 publications

Supporting

Mentioning

163

Contrasting

Order By: Relevance

“…A hybrid encoder with an attention mechanism to model the user's sequential behavior is explored. • SHAN [29]. It incorporates both users' historical stable preferences and recent shopping demands with a hierarchical attention network.…”

Section: Comparison Methodsmentioning

confidence: 99%

“…Hence it is crucial to consider both long-term preferences and short-term behaviors. Ying et al [29] and Li et al [15] both take customers' long-term preferences into account by simple combination with the current session. However, in real-world applications, customers have various and abundant shopping demands and their long-time behaviors are also complex and diverse.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SDM

Jin

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Capturing users' precise preferences is a fundamental problem in large-scale recommender system. Currently, item-based Collaborative Filtering (CF) methods are common matching approaches in industry. However, they are not effective to model dynamic and evolving preferences of users. In this paper, we propose a new sequential deep matching (SDM) model to capture users' dynamic preferences by combining short-term sessions and long-term behaviors. Compared with existing sequence-aware recommendation methods, we tackle the following two inherent problems in realworld applications: (1) there could exist multiple interest tendencies in one session.(2) long-term preferences may not be effectively fused with current session interests. Long-term behaviors are various and complex, hence those highly related to the short-term session should be kept for fusion. We propose to encode behavior sequences with two corresponding components: multi-head self-attention module to capture multiple types of interests and long-short term gated fusion module to incorporate long-term preferences. Successive items are recommended after matching between sequential user behavior vector and item embedding vectors. Offline experiments on real-world datasets show the superior performance of the proposed SDM. Moreover, SDM has been successfully deployed on online large-scale recommender system at Taobao and achieves improvements in terms of a range of commercial metrics.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SDM

Jin

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…In comparison, the influences of users' demographics have been rarely considered in existing SRSs and more efforts should be devoted into this direction. On the other hand, some hierarchical models including hierarchical embedding models [18], hierarchical RNN [13] and hierarchical attention networks [25] have been devised to incorporate the historical sub-sequences into sequential dependency learning to build more powerful SRSs. Particularly, the technical progress achieved to address this challenge will be presented in Sections 3.2 and 3.3.…”

Section: Handling User-item Interaction Sequences With Hierarchical Smentioning

confidence: 99%

“…Attention models are commonly employed in SRSs to emphasize those really relevant and important interactions in a sequence while downplaying those ones irrelevant to the next interaction. They are widely incorporated into shallow networks [19] and RNN [25] to handle interaction sequences with noise. Memory networks.…”

Section: Advanced Modelsmentioning

confidence: 99%

Sequential Recommender Systems: Challenges, Progress and Prospects

Wang

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

255

View full text Add to dashboard Cite

The emerging topic of sequential recommender systems (SRSs) has attracted increasing attention in recent years. Different from the conventional recommender systems (RSs) including collaborative filtering and content-based filtering, SRSs try to understand and model the sequential user behaviors, the interactions between users and items, and the evolution of users' preferences and item popularity over time. SRSs involve the above aspects for more precise characterization of user contexts, intent and goals, and item consumption trend, leading to more accurate, customized and dynamic recommendations. In this paper, we provide a systematic review on SRSs. We first present the characteristics of SRSs, and then summarize and categorize the key challenges in this research area, followed by the corresponding research progress consisting of the most recent and representative developments on this topic. Finally, we discuss the important research directions in this vibrant area.

show abstract

“…Chen et al [5] propose an attentive collaborative filtering framework, where each item is segmented into component-level elements, and attention scores are learned for these components for obtaining a better representation of items. Attention networks are also applied in group recommendation [2], sequential recommendation [37], review-based recommendation [4,29,32] and context-aware recommendation [26].…”

Section: Related Workmentioning

confidence: 99%

A Hierarchical Self-Attentive Model for Recommending User-Generated Item Lists

Wang

Niu

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

User-generated item lists are a popular feature of many different platforms. Examples include lists of books on Goodreads, playlists on Spotify and YouTube, collections of images on Pinterest, and lists of answers on question-answer sites like Zhihu. Recommending item lists is critical for increasing user engagement and connecting users to new items, but many approaches are designed for the item-based recommendation, without careful consideration of the complex relationships between items and lists. Hence, in this paper, we propose a novel user-generated list recommendation model called AttList. Two unique features of AttList are careful modeling of (i) hierarchical user preference, which aggregates items to characterize the list that they belong to, and then aggregates these lists to estimate the user preference, naturally fitting into the hierarchical structure of item lists; and (ii) item and list consistency, through a novel self-attentive aggregation layer designed for capturing the consistency of neighboring items and lists to better model user preference. Through experiments over three real-world datasets reflecting different kinds of user-generated item lists, we find that AttList results in significant improvements in NDCG, Precision@k, and Recall@k versus a suite of state-ofthe-art baselines. Furthermore, all code and data are available at https://github.com/heyunh2015/AttList.

show abstract

Sequential Recommender System based on Hierarchical Attention Networks

Cited by 286 publications

References 19 publications

SDM

SDM

Sequential Recommender Systems: Challenges, Progress and Prospects

A Hierarchical Self-Attentive Model for Recommending User-Generated Item Lists

Contact Info

Product

Resources

About